dsh-spider

DeepSeek Harness Skills Low risk

Auto-injects user-chosen skills into every DSH session, per prompt or once at session start, with a settings page, a composer indicator, and log-deduplicated session-start stamps; verified against DSH 0.1.3 source.

自动把所选技能注入每个 DSH 会话：每轮提示或仅在会话开始时注入一次，带设置页与输入区指示条；会话开始盖戳按会话日志去重，API 对照 DSH 0.1.3 源码验证。

How to install

DeepSeek Harness dsh plugin add github:countossbot/dsh-skill-injector

About

dsh-spider · DSH 技能自动注入 + 全网技能采集插件 🕷️ 在 DeepSeek Harness (DSH) 会话中**自动注入所选技能**——每轮提示注入，或仅在会话开始时注入一次。还会把 ~/.claude、~/.codex、~/.workbuddy 等**其他 agent 工具目录下的技能自动采集进 DSH**。设置页 + 输入区指示条，即点即存，重启保留。 **English** | 简体中文（本文档） --- ✨ 它解决什么问题 **问题一：技能是惰性的。** DSH 的技能平时只有手动 /ponytail 或模型自己调用时才加载。想让某个技能**常驻生效**就得每轮手动敲。这个插件让你**勾选一次，永久生效**。 **问题二：技能散落各处。** 你在 Claude Code、Codex、WorkBuddy、OpenCode 等各 agent 的目录（~/.claude/skills、~/.codex/skills、~/.workbuddy/skills…）里攒了一堆技能，DSH 默认只看 ~/.agents/skills 和 ~/.dsh/skills。本插件的 **spider 采集器**自动发现并注册这些目录，不用手动拷贝任何文件。设置页勾选 ponytail + i-have-adhd │ 即时写入 settings 传输层（无保存按钮，点…

GitHub ↗

Recommendation signals

45 Tool quality · Based on stars, downloads, maintenance, security and docs

– User interest · Adjusted by in-site views, install copies and download clicks

45 Overall

0views

0unique visitors

0install copies

0download clicks

0outbound clicks

Links

GitHub ↗ Report issue ↗

Basic safety check

Findings: curated 收录但无 npm 包/安装命令
Sources: curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics: dsh-plugin

Related plugins

MCP Server

Score83

mcp-server-chart

antvis/mcp-server-chart

🤖 A visualization mcp & skills contains 25+ visual charts using @antvis. Using for chart generation and data analysis.

☆ 4.4K ↓ 15.9K Skills ↗

Claude Code

Score81

superpowers

obra/superpowers

An agentic skills framework & software development methodology that works.

☆ 282.8K ↓ 1.5K Skills ↗

Claude CodeDeepSeek HarnessCodexMCP Server

Score80

ruflo

ruvnet/claude-flow

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

☆ 71.3K ↓ 81.9K Skills ↗

Claude Code

Score77

caveman

JuliusBrussee/caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

☆ 104.1K ↓ – Skills ↗